{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:HPX5BTB4IISMUW35KKOJ4OTLEW","short_pith_number":"pith:HPX5BTB4","canonical_record":{"source":{"id":"2410.01648","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2024-10-02T15:16:02Z","cross_cats_sorted":[],"title_canon_sha256":"8ea129acd8aea566a43e2ae37787da49aefb492487e00c7c0db91fc73011fca4","abstract_canon_sha256":"145dfe7fbd2c00813fee4db3658e7493fa6e045fa068237a0b502c2dae1ccd52"},"schema_version":"1.0"},"canonical_sha256":"3befd0cc3c4224ca5b7d529c9e3a6b25a88bf327be8837b94d9c207f6a42e0d0","source":{"kind":"arxiv","id":"2410.01648","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2410.01648","created_at":"2026-05-26T01:03:09Z"},{"alias_kind":"arxiv_version","alias_value":"2410.01648v2","created_at":"2026-05-26T01:03:09Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.01648","created_at":"2026-05-26T01:03:09Z"},{"alias_kind":"pith_short_12","alias_value":"HPX5BTB4IISM","created_at":"2026-05-26T01:03:09Z"},{"alias_kind":"pith_short_16","alias_value":"HPX5BTB4IISMUW35","created_at":"2026-05-26T01:03:09Z"},{"alias_kind":"pith_short_8","alias_value":"HPX5BTB4","created_at":"2026-05-26T01:03:09Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:HPX5BTB4IISMUW35KKOJ4OTLEW","target":"record","payload":{"canonical_record":{"source":{"id":"2410.01648","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2024-10-02T15:16:02Z","cross_cats_sorted":[],"title_canon_sha256":"8ea129acd8aea566a43e2ae37787da49aefb492487e00c7c0db91fc73011fca4","abstract_canon_sha256":"145dfe7fbd2c00813fee4db3658e7493fa6e045fa068237a0b502c2dae1ccd52"},"schema_version":"1.0"},"canonical_sha256":"3befd0cc3c4224ca5b7d529c9e3a6b25a88bf327be8837b94d9c207f6a42e0d0","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-26T01:03:09.143119Z","signature_b64":"0Kis+XtJMjfL8cDDdhq1mMiiAKe7rql2XOLBAp+tdNe47PhyrCbqCc2c4qRIaeBMEIb+PsenEA4MEAEPg8MuDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3befd0cc3c4224ca5b7d529c9e3a6b25a88bf327be8837b94d9c207f6a42e0d0","last_reissued_at":"2026-05-26T01:03:09.142141Z","signature_status":"signed_v1","first_computed_at":"2026-05-26T01:03:09.142141Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2410.01648","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-26T01:03:09Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"qYnpFDlUpbugyE5OtCnNJaKBPHUTmxj0cHg43X1ZPmuNuht1wljSl6P86jK8QV8Ls0vKzAVsRO3IvVP3Uxx5Dg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-02T14:12:07.922542Z"},"content_sha256":"38ba71ce36bcc35d69f4097190c2757c59682772facc3466a56e407df1b2c52e","schema_version":"1.0","event_id":"sha256:38ba71ce36bcc35d69f4097190c2757c59682772facc3466a56e407df1b2c52e"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:HPX5BTB4IISMUW35KKOJ4OTLEW","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"DeIDClinic: A Risk-Aware Pseudonymization Framework for Clinical Text De-identification and Re-identification Risk Assessment","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Angel Paul, Dhivin Shaji, Goran Nenadic, Lifeng Han, Suzan Verberne, Warren Del-Pinto","submitted_at":"2024-10-02T15:16:02Z","abstract_excerpt":"The increasing availability of sensitive textual data has created an urgent need for robust de-identification methods that enable compliant data sharing while preserving downstream utility. This paper presents DeID-Clinic, a multi-layered framework for automated pseudonymization and re-identification risk assessment of clinical free-text data. Our approach integrates domain-adapted transformer models, including BioBERT and ClinicalBERT, into the MASK de-identification framework to improve the detection and masking of protected health information (PHI). Beyond entity recognition, we introduce a"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.01648","kind":"arxiv","version":2},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2410.01648/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-26T01:03:09Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"/FAVWYBKiXENfY0h8F9ESugt2pnalit128DgCv5If/TNNX4rP3eSrGXIQbaYzuNtwqZ0P50/v9kU4A9CE1pAAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-02T14:12:07.922912Z"},"content_sha256":"ad196f1aca46f9312cf81946b1fd2ec0a9e137efbb5c123a0aea93fb6561c0f3","schema_version":"1.0","event_id":"sha256:ad196f1aca46f9312cf81946b1fd2ec0a9e137efbb5c123a0aea93fb6561c0f3"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/HPX5BTB4IISMUW35KKOJ4OTLEW/bundle.json","state_url":"https://pith.science/pith/HPX5BTB4IISMUW35KKOJ4OTLEW/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/HPX5BTB4IISMUW35KKOJ4OTLEW/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-07-02T14:12:07Z","links":{"resolver":"https://pith.science/pith/HPX5BTB4IISMUW35KKOJ4OTLEW","bundle":"https://pith.science/pith/HPX5BTB4IISMUW35KKOJ4OTLEW/bundle.json","state":"https://pith.science/pith/HPX5BTB4IISMUW35KKOJ4OTLEW/state.json","well_known_bundle":"https://pith.science/.well-known/pith/HPX5BTB4IISMUW35KKOJ4OTLEW/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:HPX5BTB4IISMUW35KKOJ4OTLEW","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"145dfe7fbd2c00813fee4db3658e7493fa6e045fa068237a0b502c2dae1ccd52","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2024-10-02T15:16:02Z","title_canon_sha256":"8ea129acd8aea566a43e2ae37787da49aefb492487e00c7c0db91fc73011fca4"},"schema_version":"1.0","source":{"id":"2410.01648","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2410.01648","created_at":"2026-05-26T01:03:09Z"},{"alias_kind":"arxiv_version","alias_value":"2410.01648v2","created_at":"2026-05-26T01:03:09Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.01648","created_at":"2026-05-26T01:03:09Z"},{"alias_kind":"pith_short_12","alias_value":"HPX5BTB4IISM","created_at":"2026-05-26T01:03:09Z"},{"alias_kind":"pith_short_16","alias_value":"HPX5BTB4IISMUW35","created_at":"2026-05-26T01:03:09Z"},{"alias_kind":"pith_short_8","alias_value":"HPX5BTB4","created_at":"2026-05-26T01:03:09Z"}],"graph_snapshots":[{"event_id":"sha256:ad196f1aca46f9312cf81946b1fd2ec0a9e137efbb5c123a0aea93fb6561c0f3","target":"graph","created_at":"2026-05-26T01:03:09Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2410.01648/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The increasing availability of sensitive textual data has created an urgent need for robust de-identification methods that enable compliant data sharing while preserving downstream utility. This paper presents DeID-Clinic, a multi-layered framework for automated pseudonymization and re-identification risk assessment of clinical free-text data. Our approach integrates domain-adapted transformer models, including BioBERT and ClinicalBERT, into the MASK de-identification framework to improve the detection and masking of protected health information (PHI). Beyond entity recognition, we introduce a","authors_text":"Angel Paul, Dhivin Shaji, Goran Nenadic, Lifeng Han, Suzan Verberne, Warren Del-Pinto","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2024-10-02T15:16:02Z","title":"DeIDClinic: A Risk-Aware Pseudonymization Framework for Clinical Text De-identification and Re-identification Risk Assessment"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.01648","kind":"arxiv","version":2},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:38ba71ce36bcc35d69f4097190c2757c59682772facc3466a56e407df1b2c52e","target":"record","created_at":"2026-05-26T01:03:09Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"145dfe7fbd2c00813fee4db3658e7493fa6e045fa068237a0b502c2dae1ccd52","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2024-10-02T15:16:02Z","title_canon_sha256":"8ea129acd8aea566a43e2ae37787da49aefb492487e00c7c0db91fc73011fca4"},"schema_version":"1.0","source":{"id":"2410.01648","kind":"arxiv","version":2}},"canonical_sha256":"3befd0cc3c4224ca5b7d529c9e3a6b25a88bf327be8837b94d9c207f6a42e0d0","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"3befd0cc3c4224ca5b7d529c9e3a6b25a88bf327be8837b94d9c207f6a42e0d0","first_computed_at":"2026-05-26T01:03:09.142141Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-26T01:03:09.142141Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"0Kis+XtJMjfL8cDDdhq1mMiiAKe7rql2XOLBAp+tdNe47PhyrCbqCc2c4qRIaeBMEIb+PsenEA4MEAEPg8MuDg==","signature_status":"signed_v1","signed_at":"2026-05-26T01:03:09.143119Z","signed_message":"canonical_sha256_bytes"},"source_id":"2410.01648","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:38ba71ce36bcc35d69f4097190c2757c59682772facc3466a56e407df1b2c52e","sha256:ad196f1aca46f9312cf81946b1fd2ec0a9e137efbb5c123a0aea93fb6561c0f3"],"state_sha256":"0ee1a8b3fc9f03089c38a276eb32dfe496feb87c0d19ce89e3c609ae012bba9a"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"UDel8h7qgndhAWjgttOBACFw7dhHttNDZv+1Tkwvh2lP1g/CNabwuOV75ULkAM0sMpnV9TI4DvaGs9Xw/jBXAg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-02T14:12:07.924946Z","bundle_sha256":"1796798fe39af73af53b542e83c4b770ba83a1bbadd7a753499f62ca7294ebf6"}}